Hugging Face's logo

moos124
/
code-reasoning-0.5b

Transformers
Safetensors
Generated from Trainer
trl
hf_jobs
sft
Model card Files
xet
 Community
moos124 commited on
Commit
ae477e3
·
verified ·
1 Parent(s): 97ee88f

Training in progress, step 100, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +13 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3e32b7ed7e73e63c9061eb2d9c83ec12e13a4db0e8978e89584edd4a684d547
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb454717f18f3a4368d7c3040ee8cc9208602f5fcab68e9b67e853914f25bb11
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8ccd0f9c3feeeb4efd7c78307285e3fe1d632bf3a6a8337fbee11bed9103cda
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1e6b83be3aaeeec6eb14808af346bd67cffb95129b57d9698d96e413b331d93
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6406d28bb797af6cc8f14cb89f9f2f9f64fe58fad4fe9f8636123f6b33db614c
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c20d77fd0f8ca8e0d959a35902916d9113e4094ff6f70fdce68809f2cc07e7d7
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ac1fec52096ad1ce96a38de42f596fccfcc0af618779f023bd68582ea436456
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d40d7ee4cb3750a04a94c1e6c33db3b3326535948996cc27f9d31f301ea90e48
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.0192,
6
  "eval_steps": 500,
7
- "global_step": 90,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -108,6 +108,16 @@
108
  "mean_token_accuracy": 0.6713629268109799,
109
  "num_tokens": 422371.0,
110
  "step": 90
 
 
 
 
 
 
 
 
 
 
111
  }
112
  ],
113
  "logging_steps": 10,
@@ -127,7 +137,7 @@
127
  "attributes": {}
128
  }
129
  },
130
- "total_flos": 2064637136492544.0,
131
  "train_batch_size": 4,
132
  "trial_name": null,
133
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.021333333333333333,
6
  "eval_steps": 500,
7
+ "global_step": 100,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
108
  "mean_token_accuracy": 0.6713629268109799,
109
  "num_tokens": 422371.0,
110
  "step": 90
111
+ },
112
+ {
113
+ "entropy": 1.467514592409134,
114
+ "epoch": 0.021333333333333333,
115
+ "grad_norm": 0.5295536518096924,
116
+ "learning_rate": 3.3e-05,
117
+ "loss": 1.576413631439209,
118
+ "mean_token_accuracy": 0.6885988213121891,
119
+ "num_tokens": 462284.0,
120
+ "step": 100
121
  }
122
  ],
123
  "logging_steps": 10,
 
137
  "attributes": {}
138
  }
139
  },
140
+ "total_flos": 2246830085434368.0,
141
  "train_batch_size": 4,
142
  "trial_name": null,
143
  "trial_params": null